舉報

會員
Hands-On Meta Learning with Python
Metalearningisanexcitingresearchtrendinmachinelearning,whichenablesamodeltounderstandthelearningprocess.UnlikeotherMLparadigms,withmetalearningyoucanlearnfromsmalldatasetsfaster.Hands-OnMetaLearningwithPythonstartsbyexplainingthefundamentalsofmetalearningandhelpsyouunderstandtheconceptoflearningtolearn.Youwilldelveintovariousone-shotlearningalgorithms,likesiamese,prototypical,relationandmemory-augmentednetworksbyimplementingtheminTensorFlowandKeras.Asyoumakeyourwaythroughthebook,youwilldiveintostate-of-the-artmetalearningalgorithmssuchasMAML,Reptile,andCAML.YouwillthenexplorehowtolearnquicklywithMeta-SGDanddiscoverhowyoucanperformunsupervisedlearningusingmetalearningwithCACTUs.Intheconcludingchapters,youwillworkthroughrecenttrendsinmetalearningsuchasadversarialmetalearning,taskagnosticmetalearning,andmetaimitationlearning.Bytheendofthisbook,youwillbefamiliarwithstate-of-the-artmetalearningalgorithmsandabletoenablehuman-likecognitionforyourmachinelearningmodels.
最新章節
- Leave a review - let other readers know what you think
- Other Books You May Enjoy
- Chapter 9: Recent Advancements and Next Steps
- Chapter 8: Gradient Agreement as an Optimization Objective
- Chapter 7: Meta-SGD and Reptile Algorithms
- Chapter 6: MAML and Its Variants
品牌:中圖公司
上架時間:2021-07-02 12:35:57
出版社:Packt Publishing
本書數字版權由中圖公司提供,并由其授權上海閱文信息技術有限公司制作發行